Korean Stereotype Content Model: Translating Stereotypes Across Cultures

AbstractTo address bias in language models, researchers are leveraging established social psychology research on stereotyping. This interdisciplinary approach uses frameworks like the Stereotype Content Model (SCM) to understand how stereotypes about social groups are formed and perpetuated. The SCM posits that stereotypes are based on two dimensions: warmth (intent to harm) and competence (ability to harm). This framework has been applied in NLP for various tasks, including stereotype identification, bias mitigation, and hate speech detection. While the SCM has been extensively studied in English language models and Western cultural contexts, its applicability as a cross-cultural measure of stereotypes remains an open research question. This paper explores the cross-cultural validity of the SCM by developing a Korean Stereotype Content Model (KoSCM). We create a Korean warmth-competence lexicon through machine translation of existing English lexicons, validated by an expert translator, and utilize this lexicon to develop a labeled training dataset of Korean sentences. This work presents the first extension of SCM lexicons to a non-English language (Korean), aiming to broaden understanding of stereotypes and cultural dynamics.